canva-incident-runbook

Warn

Audited by Snyk on May 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). SKILL.md explicitly instructs fetching and checking public third‑party sources — e.g., "Check Canva developer community for reported outages" and checking Canva status pages and API responses in the Quick Triage/5xx sections — which requires the agent to read untrusted, user-generated/public web content as part of its incident-decision workflow.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 20, 2026, 12:02 AM
Issues
1
Security Audit — snyk — canva-incident-runbook